仅用一次人类示范，让机器人学会复杂操作任务。
DemoDiffusion: One-Shot Human Imitation using pre-trained Diffusion Policy
- 用人体动作生成机器人初始轨迹，再通过扩散模型优化。
- 真实场景下8项任务平均成功率83.8%，远超基线方法。
- 无需额外训练或配对数据，适合快速部署新任务。
我们提出DemoDiffusion，一种仅需单次人类示范即可让机器人完成操作任务的新方法，无需任务特定训练或成对的人机数据。该方法基于两个核心洞察：首先，人体示范中的手部运动可作为机器人末端执行器轨迹的有用先验，通过运动学重定向转换为粗略的开环机器人轨迹；其次，尽管该重定向轨迹捕捉了任务的整体结构，但可能与实际可行的机器人动作不一致。为此，我们利用预训练的通用扩散策略对轨迹进行修正，确保其既遵循人类动作又处于合理机器人动作分布内。相比基于在线强化学习或成对人机数据的方法，本方法可在极少投入下实现对新任务和新场景的鲁棒适应。在8个不同操作任务的真实世界实验中，DemoDiffusion平均成功率达83.8%，远高于预训练策略的13.8%和运动学重定向的52.5%，甚至在预训练策略完全失败的任务上也成功完成。
原文摘要 · Abstract (English)
We propose DemoDiffusion, a simple method for enabling robots to perform manipulation tasks by imitating a single human demonstration, without requiring task-specific training or paired human-robot data. Our approach is based on two insights. First, the hand motion in a human demonstration provides a useful prior for the robot's end-effector trajectory, which we can convert into a rough open-loop robot motion trajectory via kinematic retargeting. Second, while this retargeted motion captures the overall structure of the task, it may not align well with plausible robot actions in-context. To address this, we leverage a pre-trained generalist diffusion policy to modify the trajectory, ensuring it both follows the human motion and remains within the distribution of plausible robot actions. Unlike approaches based on online reinforcement learning or paired human-robot data, our method enables robust adaptation to new tasks and scenes with minimal effort. In real-world experiments across 8 diverse manipulation tasks, DemoDiffusion achieves 83.8\% average success rate, compared to 13.8\% for the pre-trained policy and 52.5\% for kinematic retargeting, succeeding even on tasks where the pre-trained generalist policy fails entirely. Project page: https://demodiffusion.github.io/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。